hands-on-deep-learning-with-go

module
v0.0.0-...-f9a494f Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: Sep 3, 2019 License: MIT

README

Hands-On Deep Learning with Go

Hands-On Deep Learning with Go

This is the code repository for Hands-On Deep Learning with Go, published by Packt.

A practical approach to building neural network models using Gorgonia.

What is this book about?

The Go ecosystem comprises some really powerful Deep Learning tools. This book shows you how to use these tools to train and deploy scalable Deep Learning models. You will explore a number of modern Neural Network architectures such as CNNs, RNNs, and more. By the end, you will be able to train your own Deep Learning models from scratch, using the power of Go.

This book covers the following exciting features:

  • Explore the Go ecosystem of libraries and communities for deep learning
  • Get to grips with Neural Networks, their history, and how they work
  • Design and implement Deep Neural Networks in Go
  • Get a strong foundation of concepts such as Backpropagation and Momentum
  • Build Variational Autoencoders and Restricted Boltzmann Machines using Go
  • Build models with CUDA and benchmark CPU and GPU models

If you feel this book is for you, get your copy today!

Instructions and Navigations

All of the code is organized into folders. For example, Chapter02.

The code will look like the following:

type nn struct {
    g *ExprGraph
    w0, w1 *Node

    pred *Node
}

Following is what you need for this book: This book is for machine learning engineers, data analysts, data scientists interested in deep learning and are looking to explore implementing advanced algorithms in PyTorch. Some knowledge of machine learning is helpful but not a mandatory need. Working knowledge of Python programming is expected.

With the following software and hardware list you can run all code files present in the book (Chapter 1-10).

Software and Hardware List
Chapter Software required OS required
All Gorgonia package for Go Windows, Mac OS X, and Linux (Any)
4,6 Cu package for Go Windows, Mac OS X, and Linux (Any)
4,6 CUDA (plus drivers) from NVIDIA Windows, Mac OS X, and Linux (Any)
4,6 NVIDIA GPU that supports CUDA Windows, Mac OS X, and Linux (Any)
9 Docker Windows, Mac OS X, and Linux (Any)
10 AWS Account, Kubernetes/Docker/kops, Pachyderm Windows, Mac OS X, and Linux (Any)

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it.

Get to Know the Authors

Gareth Seneque is a machine learning engineer with 11 years' experience of building and deploying systems at scale in the finance and media industries. He became interested in deep learning in 2014 and is currently building a search platform within his organization, using neuro-linguistic programming and other machine learning techniques to generate content metadata and drive recommendations. He has contributed to a number of open source projects, including CoREBench and Gorgonia. He also has extensive experience with modern DevOps practices, using AWS, Docker, and Kubernetes to effectively distribute the processing of machine learning workloads.

Darrell Chua is a senior data scientist with more than 10 years' experience. He has developed models of varying complexity, from building credit scorecards with logistic regression to creating image classification models for trading cards. He has spent the majority of his time working with in fintech companies, trying to bring machine learning technologies into the world of finance. He has been programming in Go for several years and has been working on deep learning models for even longer. Among his achievements is the creation of numerous business intelligence and data science pipelines that enable the delivery of a top-of-the-line automated underwriting system, producing near-instant approval decisions.

Suggestions and Feedback

Click here if you have any feedback or suggestions.

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL